Trend-Adjusted Time Series Models with an Application to Gold Price Forecasting

TL;DR

This paper introduces the Trend-Adjusted Time Series (TATS) model, which improves gold price forecasting by separately predicting trends and values, then adjusting forecasts accordingly, outperforming standard neural network models.

Contribution

The paper proposes the TATS model that combines trend prediction with value forecasting, offering a novel approach to enhance time series accuracy, validated through theoretical and empirical analysis.

Findings

TATS outperforms LSTM and Bi-LSTM in forecasting accuracy.

Incorporating trend detection improves model performance.

Traditional metrics like MSE and MAE are insufficient alone.

Abstract

Time series data play a critical role in various fields, including finance, healthcare, marketing, and engineering. A wide range of techniques (from classical statistical models to neural network-based approaches such as Long Short-Term Memory (LSTM)) have been employed to address time series forecasting challenges. In this paper, we reframe time series forecasting as a two-part task: (1) predicting the trend (directional movement) of the time series at the next time step, and (2) forecasting the quantitative value at the next time step. The trend can be predicted using a binary classifier, while quantitative values can be forecasted using models such as LSTM and Bidirectional Long Short-Term Memory (Bi-LSTM). Building on this reframing, we propose the Trend-Adjusted Time Series (TATS) model, which adjusts the forecasted values based on the predicted trend provided by the binary classifier. We validate the proposed approach through both theoretical analysis and empirical evaluation. The TATS model is applied to a volatile financial time series (the daily gold price) with the objective of forecasting the next days price. Experimental results demonstrate that TATS consistently outperforms standard LSTM and Bi-LSTM models by achieving significantly lower forecasting error. In addition, our results indicate that commonly used metrics such as MSE and MAE are insufficient for fully assessing time series model performance. Therefore, we also incorporate trend detection accuracy, which measures how effectively a model captures trends in a time series.